Short-term forecasting of urban transport hubs based on mobile phone signaling data

LIN Peiqun; LEI Yongwei; ZHANG Zi; CHEN Litian

doi:10.11918/j.issn.0367-6234.201704082

Chinese

您当前的位置：

首页 >

文章列表页 >

Short-term forecasting of urban transport hubs based on mobile phone signaling data

更新时间：2026-10-23

- Short-term forecasting of urban transport hubs based on mobile phone signaling data
- Vol. 50, Issue 9, Pages: 89-95(2018)
- 作者机构：
  
  1. 华南理工大学土木与交通学院,广州,510641
  2. 广东省交通规划设计研究院股份有限公司,广州,510507
  3. 广州市交通委员会,广州,510620
- 作者简介：
- 基金信息：
- DOI：10.11918/j.issn.0367-6234.201704082
  CLC： U491
- Published：2018
- 稿件说明：
移动端阅览
LIN Peiqun, LEI Yongwei, ZHANG Zi, et al. Short-term forecasting of urban transport hubs based on mobile phone signaling data[J]. 2018, 50(9): 89-95.
DOI：

LIN Peiqun, LEI Yongwei, ZHANG Zi, et al. Short-term forecasting of urban transport hubs based on mobile phone signaling data[J]. 2018, 50(9): 89-95. DOI： 10.11918/j.issn.0367-6234.201704082.

摘要

为实现对重点区域人群聚集动态的有效掌握，保障区域人群的及时疏运，预防群体性安全事故的发生，以广州市火车站枢纽区域为例，通过对海量手机信令数据进行信息处理，结合地理信息系统将手机信令数据映射至研究区域，实现区域人流量的实时统计，同时分析了大都市火车站枢纽区域春运人流量变化情况，得出春运期间区域人流量存在周期性变化的规律，以此为基础，构建了以平均绝对百分比误差最小的k值自适应计算模型，设计了基于手机信令数据的城市交通枢纽人流量k近邻预测算法，并以节假日与非节假日两种不同交通模式环境进行算法测试.结果表明：所建立的预测算法在两种模式下其平均绝对百分比误差PMAPE分别在6%与5%以内，均能够较为准确地对区域人流量进行预测.

Abstract

To effectively grasp the dynamic information of key regional population aggregation

guarantee timely dispatching of regional population

and prevent group security accident

this paper took Guangzhou Railway Station hub area as an example

and obtained real-time statistics of its regional population by carrying out information processing based on massive mobile phone signaling data and mapping the data to the study area using geographic information system. Meanwhile

it analyzed the change of the population in this area during Spring Festival

and summarized the periodic variation characteristics of the regional population. Based on this

this paper constructed the k value adaptive calculation model with minimum absolute percentage error

and built the k-Nearest Neighborhood algorithm based on the mobile communication data to predict urban hub traffic. The algorithm was tested under the traffic conditions on weekends and weekdays near Guangzhou Railway Station. The results showed that the average absolute percentage error (MAPE) of the prediction algorithm was around 5%. It is more accurate to effectively predict regional population.

关键词

Keywords

references

Views

214

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Generative face detection algorithm based on multi-scale fusion and receptive field enhancement

Estimation method of heterogeneous treatment effect with multiple treatment

A multi-class classification model for network intrusion detection

Low-complexity single-snapshot DOA estimation algorithm for one-dimensional linear arrays

Dynamic liquid level prediction using virtual samples generated by FD-constrained transfer

Related Author

No data

Related Institution

No data

AI问答

Postal code：100079
Tel：（010）53879206 Email：tmw@bjxintong.com.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09082226号-64 京公网安备11010602201714号
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰